Quantum-Eyes: Scalable Quantum Convolutional Neural Networks for Low-Overhead Object Detection [Research Frontier]

Quantum neural networks (QNNs) are gaining attention as a promising foundation for next-generation machine learning. However, the practical deployment of QNNs, particularly in vision tasks, remains limited due to hardware constraints such as qubit scarcity. To address this challenge, this paper proposes a quantum convolutional neural network (QCNN)-based object detection framework designed for the noisy intermediate scale quantum (NISQ) era. The proposed method introduces four key components, patch processing, channel uploading, hybrid channel construction, and heterogeneous knowledge distillation, to enable efficient multi-channel object detection with a limited number of qubits. Furthermore, the knowledge distillation strategy facilitates the transfer of knowledge from a classical region proposal network (RPN) to its quantum counterpart, thereby enhancing detection accuracy despite the limitations of early-stage quantum machine learning. The evaluation results demonstrate the feasibility and efficiency of the proposed quantum object detection model, which can be effectively applied to complex vision tasks within existing quantum hardware limitations.